[ https://issues.apache.org/jira/browse/SPARK-20784?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Mathieu D updated SPARK-20784: ------------------------------ Description: Spark hangs and stop executing any job or task. Web UI shows 0 active task on executors. Our application runs several spark contexts for several users in parallel in threads. spark version 2.0.2, yarn-client Extract of thread stack below. {noformat} "ForkJoinPool-1-worker-0" #107 daemon prio=5 os_prio=0 tid=0x00007fddf0005800 nid=0x484 waiting on condition [0x00007fddd0bf 6000] java.lang.Thread.State: WAITING (parking) at sun.misc.Unsafe.park(Native Method) - parking to wait for <0x000000078c232760> (a scala.concurrent.impl.Promise$CompletionLatch) at java.util.concurrent.locks.LockSupport.park(LockSupport.java:175) at java.util.concurrent.locks.AbstractQueuedSynchronizer.parkAndCheckInterrupt(AbstractQueuedSynchronizer.java:836) at java.util.concurrent.locks.AbstractQueuedSynchronizer.doAcquireSharedInterruptibly(AbstractQueuedSynchronizer.java:997) at java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1304) at scala.concurrent.impl.Promise$DefaultPromise.tryAwait(Promise.scala:202) at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:218) at scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223) at org.apache.spark.util.ThreadUtils$.awaitResultInForkJoinSafely(ThreadUtils.scala:212) at org.apache.spark.sql.execution.exchange.BroadcastExchangeExec.doExecuteBroadcast(BroadcastExchangeExec.scala:120) at org.apache.spark.sql.execution.InputAdapter.doExecuteBroadcast(WholeStageCodegenExec.scala:229) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.executeBroadcast(SparkPlan.scala:124) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.prepareBroadcast(BroadcastHashJoinExec.scala:98) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.codegenInner(BroadcastHashJoinExec.scala:197) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doConsume(BroadcastHashJoinExec.scala:82) at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153) at org.apache.spark.sql.execution.ProjectExec.consume(basicPhysicalOperators.scala:30) at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:62) at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153) at org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:218) at org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:244) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:218) at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doProduce(BroadcastHashJoinExec.scala:77) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.produce(BroadcastHashJoinExec.scala:38) at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30) at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:309) at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:347) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) at org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:87) at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:123) at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:114) at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52) at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:114) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:233) at org.apache.spark.sql.execution.SortExec.inputRDDs(SortExec.scala:111) at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:361) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) at org.apache.spark.sql.execution.columnar.InMemoryRelation.buildBuffers(InMemoryRelation.scala:97) at org.apache.spark.sql.execution.columnar.InMemoryRelation.<init>(InMemoryRelation.scala:86) at org.apache.spark.sql.execution.columnar.InMemoryRelation$.apply(InMemoryRelation.scala:42) at org.apache.spark.sql.execution.CacheManager$$anonfun$cacheQuery$1.apply(CacheManager.scala:98) at org.apache.spark.sql.execution.CacheManager.writeLock(CacheManager.scala:65) at org.apache.spark.sql.execution.CacheManager.cacheQuery(CacheManager.scala:89) at org.apache.spark.sql.Dataset.persist(Dataset.scala:2301) at org.apache.spark.sql.Dataset.cache(Dataset.scala:2311) at com.bluedme.woda.ng.matcher.StrictMatchStrategy.buildJoinMap(StrictMatchStrategy.scala:172) at com.bluedme.woda.ng.matcher.Matcher$$anonfun$evaluateMatching$1$$anonfun$apply$5$$anonfun$apply$6.apply(Matcher.scala:137) at com.bluedme.woda.ng.matcher.Matcher$$anonfun$evaluateMatching$1$$anonfun$apply$5$$anonfun$apply$6.apply(Matcher.scala:137) at scala.concurrent.impl.Future$PromiseCompletingRunnable.liftedTree1$1(Future.scala:24) at scala.concurrent.impl.Future$PromiseCompletingRunnable.run(Future.scala:24) at java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1402) at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289) at java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056) at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692) at java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:157) {noformat} jstack -F does not mention any deadlock. It already happened a couple of times, with similar stack (CompletionLatch), but not always the same path in our application. was: Spark hangs and stop executing any job or task. Web UI shows 0 active task on executors. Our application runs several spark contexts for several users in parallel in threads. spark version 2.0.2, yarn-client Extract of thread stack below. {norformat} "ForkJoinPool-1-worker-0" #107 daemon prio=5 os_prio=0 tid=0x00007fddf0005800 nid=0x484 waiting on condition [0x00007fddd0bf 6000] java.lang.Thread.State: WAITING (parking) at sun.misc.Unsafe.park(Native Method) - parking to wait for <0x000000078c232760> (a scala.concurrent.impl.Promise$CompletionLatch) at java.util.concurrent.locks.LockSupport.park(LockSupport.java:175) at java.util.concurrent.locks.AbstractQueuedSynchronizer.parkAndCheckInterrupt(AbstractQueuedSynchronizer.java:836) at java.util.concurrent.locks.AbstractQueuedSynchronizer.doAcquireSharedInterruptibly(AbstractQueuedSynchronizer.jav a:997) at java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java: 1304) at scala.concurrent.impl.Promise$DefaultPromise.tryAwait(Promise.scala:202) at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:218) at scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223) at org.apache.spark.util.ThreadUtils$.awaitResultInForkJoinSafely(ThreadUtils.scala:212) at org.apache.spark.sql.execution.exchange.BroadcastExchangeExec.doExecuteBroadcast(BroadcastExchangeExec.scala:120) at org.apache.spark.sql.execution.InputAdapter.doExecuteBroadcast(WholeStageCodegenExec.scala:229) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.executeBroadcast(SparkPlan.scala:124) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.prepareBroadcast(BroadcastHashJoinExec.scala:98) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.codegenInner(BroadcastHashJoinExec.scala:197) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doConsume(BroadcastHashJoinExec.scala:82) at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153) at org.apache.spark.sql.execution.ProjectExec.consume(basicPhysicalOperators.scala:30) at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:62) at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153) at org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:218) at org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:244) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:218) at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doProduce(BroadcastHashJoinExec.scala:77) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.produce(BroadcastHashJoinExec.scala:38) at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30) at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:309) at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:347) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) at org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:87) at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:123) at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:114) at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52) at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:114) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:233) at org.apache.spark.sql.execution.SortExec.inputRDDs(SortExec.scala:111) at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:361) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) at org.apache.spark.sql.execution.columnar.InMemoryRelation.buildBuffers(InMemoryRelation.scala:97) at org.apache.spark.sql.execution.columnar.InMemoryRelation.<init>(InMemoryRelation.scala:86) at org.apache.spark.sql.execution.columnar.InMemoryRelation$.apply(InMemoryRelation.scala:42) at org.apache.spark.sql.execution.CacheManager$$anonfun$cacheQuery$1.apply(CacheManager.scala:98) at org.apache.spark.sql.execution.CacheManager.writeLock(CacheManager.scala:65) at org.apache.spark.sql.execution.CacheManager.cacheQuery(CacheManager.scala:89) at org.apache.spark.sql.Dataset.persist(Dataset.scala:2301) at org.apache.spark.sql.Dataset.cache(Dataset.scala:2311) at com.bluedme.woda.ng.matcher.StrictMatchStrategy.buildJoinMap(StrictMatchStrategy.scala:172) at com.bluedme.woda.ng.matcher.Matcher$$anonfun$evaluateMatching$1$$anonfun$apply$5$$anonfun$apply$6.apply(Matcher.scala:137) at com.bluedme.woda.ng.matcher.Matcher$$anonfun$evaluateMatching$1$$anonfun$apply$5$$anonfun$apply$6.apply(Matcher.scala:137) at scala.concurrent.impl.Future$PromiseCompletingRunnable.liftedTree1$1(Future.scala:24) at scala.concurrent.impl.Future$PromiseCompletingRunnable.run(Future.scala:24) at java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1402) at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289) at java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056) at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692) at java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:157) {noformat} It already happened a couple of times, with similar stack (CompletionLatch), but not always the same path in our application. > Spark hangs forever / potential deadlock ? > ------------------------------------------ > > Key: SPARK-20784 > URL: https://issues.apache.org/jira/browse/SPARK-20784 > Project: Spark > Issue Type: Bug > Components: Spark Core > Affects Versions: 2.0.2 > Reporter: Mathieu D > > Spark hangs and stop executing any job or task. > Web UI shows 0 active task on executors. > Our application runs several spark contexts for several users in parallel in > threads. > spark version 2.0.2, yarn-client > Extract of thread stack below. > {noformat} > "ForkJoinPool-1-worker-0" #107 daemon prio=5 os_prio=0 tid=0x00007fddf0005800 > nid=0x484 waiting on condition [0x00007fddd0bf > 6000] > java.lang.Thread.State: WAITING (parking) > at sun.misc.Unsafe.park(Native Method) > - parking to wait for <0x000000078c232760> (a > scala.concurrent.impl.Promise$CompletionLatch) > at java.util.concurrent.locks.LockSupport.park(LockSupport.java:175) > at > java.util.concurrent.locks.AbstractQueuedSynchronizer.parkAndCheckInterrupt(AbstractQueuedSynchronizer.java:836) > at > java.util.concurrent.locks.AbstractQueuedSynchronizer.doAcquireSharedInterruptibly(AbstractQueuedSynchronizer.java:997) > at > java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1304) > at > scala.concurrent.impl.Promise$DefaultPromise.tryAwait(Promise.scala:202) > at > scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:218) > at > scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223) > at > org.apache.spark.util.ThreadUtils$.awaitResultInForkJoinSafely(ThreadUtils.scala:212) > at > org.apache.spark.sql.execution.exchange.BroadcastExchangeExec.doExecuteBroadcast(BroadcastExchangeExec.scala:120) > at > org.apache.spark.sql.execution.InputAdapter.doExecuteBroadcast(WholeStageCodegenExec.scala:229) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.SparkPlan.executeBroadcast(SparkPlan.scala:124) > at > org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.prepareBroadcast(BroadcastHashJoinExec.scala:98) > at > org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.codegenInner(BroadcastHashJoinExec.scala:197) > at > org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doConsume(BroadcastHashJoinExec.scala:82) > at > org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153) > at > org.apache.spark.sql.execution.ProjectExec.consume(basicPhysicalOperators.scala:30) > at > org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:62) > at > org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153) > at > org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:218) > at > org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:244) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:218) > at > org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30) > at > org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doProduce(BroadcastHashJoinExec.scala:77) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.produce(BroadcastHashJoinExec.scala:38) > at > org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83) > at > org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78) > at > org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30) > at > org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:309) > at > org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:347) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) > at > org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:87) > at > org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:123) > at > org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:114) > at > org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52) > at > org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:114) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) > at > org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:233) > at > org.apache.spark.sql.execution.SortExec.inputRDDs(SortExec.scala:111) > at > org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:361) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114) > at > org.apache.spark.sql.execution.columnar.InMemoryRelation.buildBuffers(InMemoryRelation.scala:97) > at > org.apache.spark.sql.execution.columnar.InMemoryRelation.<init>(InMemoryRelation.scala:86) > at > org.apache.spark.sql.execution.columnar.InMemoryRelation$.apply(InMemoryRelation.scala:42) > at > org.apache.spark.sql.execution.CacheManager$$anonfun$cacheQuery$1.apply(CacheManager.scala:98) > at > org.apache.spark.sql.execution.CacheManager.writeLock(CacheManager.scala:65) > at > org.apache.spark.sql.execution.CacheManager.cacheQuery(CacheManager.scala:89) > at org.apache.spark.sql.Dataset.persist(Dataset.scala:2301) > at org.apache.spark.sql.Dataset.cache(Dataset.scala:2311) > at > com.bluedme.woda.ng.matcher.StrictMatchStrategy.buildJoinMap(StrictMatchStrategy.scala:172) > at > com.bluedme.woda.ng.matcher.Matcher$$anonfun$evaluateMatching$1$$anonfun$apply$5$$anonfun$apply$6.apply(Matcher.scala:137) > at > com.bluedme.woda.ng.matcher.Matcher$$anonfun$evaluateMatching$1$$anonfun$apply$5$$anonfun$apply$6.apply(Matcher.scala:137) > at > scala.concurrent.impl.Future$PromiseCompletingRunnable.liftedTree1$1(Future.scala:24) > at > scala.concurrent.impl.Future$PromiseCompletingRunnable.run(Future.scala:24) > at > java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1402) > at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289) > at > java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056) > at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692) > at > java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:157) > {noformat} > jstack -F does not mention any deadlock. > It already happened a couple of times, with similar stack (CompletionLatch), > but not always the same path in our application. -- This message was sent by Atlassian JIRA (v6.3.15#6346) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org